Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma fixes from Jason Gunthorpe:
 "A number of driver bug fixes and a few recent regressions:

   - Several bug fixes for bnxt_re. Crashing, incorrect data reported,
     and corruption on new HW

   - Memory leak and crash in rxe

   - Fix sysfs corruption in rxe if the netdev name is too long

   - Fix a crash on error unwind in the new cq_pool code

   - Fix kobject panics in rtrs by working device lifetime properly

   - Fix a data corruption bug in iser target related to misaligned
     buffers"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  IB/isert: Fix unaligned immediate-data handling
  RDMA/rtrs-srv: Set .release function for rtrs srv device during device init
  RDMA/bnxt_re: Remove set but not used variable 'qplib_ctx'
  RDMA/core: Fix reported speed and width
  RDMA/core: Fix unsafe linked list traversal after failing to allocate CQ
  RDMA/bnxt_re: Remove the qp from list only if the qp destroy succeeds
  RDMA/bnxt_re: Fix driver crash on unaligned PSN entry address
  RDMA/bnxt_re: Restrict the max_gids to 256
  RDMA/bnxt_re: Static NQ depth allocation
  RDMA/bnxt_re: Fix the qp table indexing
  RDMA/bnxt_re: Do not report transparent vlan from QP1
  RDMA/mlx4: Read pkey table length instead of hardcoded value
  RDMA/rxe: Fix panic when calling kmem_cache_create()
  RDMA/rxe: Fix memleak in rxe_mem_init_user
  RDMA/rxe: Fix the parent sysfs read when the interface has 15 chars
  RDMA/rtrs-srv: Replace device_register with device_initialize and device_add

drivers/infiniband/core/cq.c

@@ -379,7 +379,7 @@ static int ib_alloc_cqs(struct ib_device *dev, unsigned int nr_cqes,
 {
 	LIST_HEAD(tmp_list);
 	unsigned int nr_cqs, i;
-	struct ib_cq *cq;
+	struct ib_cq *cq, *n;
 	int ret;
 
 	if (poll_ctx > IB_POLL_LAST_POOL_TYPE) {
@@ -412,7 +412,7 @@ static int ib_alloc_cqs(struct ib_device *dev, unsigned int nr_cqes,
 	return 0;
 
 out_free_cqs:
-	list_for_each_entry(cq, &tmp_list, pool_entry) {
+	list_for_each_entry_safe(cq, n, &tmp_list, pool_entry) {
 		cq->shared = false;
 		ib_free_cq(cq);
 	}

drivers/infiniband/core/verbs.c

@@ -1801,7 +1801,7 @@ int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width)
 
 	dev_put(netdev);
 
-	if (!rc) {
+	if (!rc && lksettings.base.speed != (u32)SPEED_UNKNOWN) {
 		netdev_speed = lksettings.base.speed;
 	} else {
 		netdev_speed = SPEED_1000;

drivers/infiniband/hw/bnxt_re/ib_verbs.c

@@ -752,12 +752,6 @@ static int bnxt_re_destroy_gsi_sqp(struct bnxt_re_qp *qp)
 	gsi_sqp = rdev->gsi_ctx.gsi_sqp;
 	gsi_sah = rdev->gsi_ctx.gsi_sah;
 
-	/* remove from active qp list */
-	mutex_lock(&rdev->qp_lock);
-	list_del(&gsi_sqp->list);
-	mutex_unlock(&rdev->qp_lock);
-	atomic_dec(&rdev->qp_count);
-
 	ibdev_dbg(&rdev->ibdev, "Destroy the shadow AH\n");
 	bnxt_qplib_destroy_ah(&rdev->qplib_res,
 			      &gsi_sah->qplib_ah,
@@ -772,6 +766,12 @@ static int bnxt_re_destroy_gsi_sqp(struct bnxt_re_qp *qp)
 	}
 	bnxt_qplib_free_qp_res(&rdev->qplib_res, &gsi_sqp->qplib_qp);
 
+	/* remove from active qp list */
+	mutex_lock(&rdev->qp_lock);
+	list_del(&gsi_sqp->list);
+	mutex_unlock(&rdev->qp_lock);
+	atomic_dec(&rdev->qp_count);
+
 	kfree(rdev->gsi_ctx.sqp_tbl);
 	kfree(gsi_sah);
 	kfree(gsi_sqp);
@@ -792,11 +792,6 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata)
 	unsigned int flags;
 	int rc;
 
-	mutex_lock(&rdev->qp_lock);
-	list_del(&qp->list);
-	mutex_unlock(&rdev->qp_lock);
-	atomic_dec(&rdev->qp_count);
-
 	bnxt_qplib_flush_cqn_wq(&qp->qplib_qp);
 
 	rc = bnxt_qplib_destroy_qp(&rdev->qplib_res, &qp->qplib_qp);
@@ -819,6 +814,11 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata)
 			goto sh_fail;
 	}
 
+	mutex_lock(&rdev->qp_lock);
+	list_del(&qp->list);
+	mutex_unlock(&rdev->qp_lock);
+	atomic_dec(&rdev->qp_count);
+
 	ib_umem_release(qp->rumem);
 	ib_umem_release(qp->sumem);
 
@@ -3264,6 +3264,19 @@ static void bnxt_re_process_res_rawqp1_wc(struct ib_wc *wc,
 	wc->wc_flags |= IB_WC_GRH;
 }
 
+static bool bnxt_re_check_if_vlan_valid(struct bnxt_re_dev *rdev,
+					u16 vlan_id)
+{
+	/*
+	 * Check if the vlan is configured in the host.  If not configured, it
+	 * can be a transparent VLAN. So dont report the vlan id.
+	 */
+	if (!__vlan_find_dev_deep_rcu(rdev->netdev,
+				      htons(ETH_P_8021Q), vlan_id))
+		return false;
+	return true;
+}
+
 static bool bnxt_re_is_vlan_pkt(struct bnxt_qplib_cqe *orig_cqe,
 				u16 *vid, u8 *sl)
 {
@@ -3332,9 +3345,11 @@ static void bnxt_re_process_res_shadow_qp_wc(struct bnxt_re_qp *gsi_sqp,
 	wc->src_qp = orig_cqe->src_qp;
 	memcpy(wc->smac, orig_cqe->smac, ETH_ALEN);
 	if (bnxt_re_is_vlan_pkt(orig_cqe, &vlan_id, &sl)) {
-		wc->vlan_id = vlan_id;
-		wc->sl = sl;
-		wc->wc_flags |= IB_WC_WITH_VLAN;
+		if (bnxt_re_check_if_vlan_valid(rdev, vlan_id)) {
+			wc->vlan_id = vlan_id;
+			wc->sl = sl;
+			wc->wc_flags |= IB_WC_WITH_VLAN;
+		}
 	}
 	wc->port_num = 1;
 	wc->vendor_err = orig_cqe->status;

drivers/infiniband/hw/bnxt_re/main.c

@@ -1009,7 +1009,6 @@ static void bnxt_re_free_res(struct bnxt_re_dev *rdev)
 static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
 {
 	struct bnxt_re_ring_attr rattr = {};
-	struct bnxt_qplib_ctx *qplib_ctx;
 	int num_vec_created = 0;
 	int rc = 0, i;
 	u8 type;
@@ -1032,13 +1031,11 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev)
 	if (rc)
 		goto dealloc_res;
 
-	qplib_ctx = &rdev->qplib_ctx;
 	for (i = 0; i < rdev->num_msix - 1; i++) {
 		struct bnxt_qplib_nq *nq;
 
 		nq = &rdev->nq[i];
-		nq->hwq.max_elements = (qplib_ctx->cq_count +
-					qplib_ctx->srqc_count + 2);
+		nq->hwq.max_elements = BNXT_QPLIB_NQE_MAX_CNT;
 		rc = bnxt_qplib_alloc_nq(&rdev->qplib_res, &rdev->nq[i]);
 		if (rc) {
 			ibdev_err(&rdev->ibdev, "Alloc Failed NQ%d rc:%#x",

drivers/infiniband/hw/bnxt_re/qplib_fp.c

@@ -818,6 +818,7 @@ int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 	u16 cmd_flags = 0;
 	u32 qp_flags = 0;
 	u8 pg_sz_lvl;
+	u32 tbl_indx;
 	int rc;
 
 	RCFW_CMD_PREP(req, CREATE_QP1, cmd_flags);
@@ -907,8 +908,9 @@ int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 		rq->dbinfo.db = qp->dpi->dbr;
 		rq->dbinfo.max_slot = bnxt_qplib_set_rq_max_slot(rq->wqe_size);
 	}
-	rcfw->qp_tbl[qp->id].qp_id = qp->id;
-	rcfw->qp_tbl[qp->id].qp_handle = (void *)qp;
+	tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw);
+	rcfw->qp_tbl[tbl_indx].qp_id = qp->id;
+	rcfw->qp_tbl[tbl_indx].qp_handle = (void *)qp;
 
 	return 0;
 
@@ -935,10 +937,10 @@ static void bnxt_qplib_init_psn_ptr(struct bnxt_qplib_qp *qp, int size)
 
 	sq = &qp->sq;
 	hwq = &sq->hwq;
+	/* First psn entry */
 	fpsne = (u64)bnxt_qplib_get_qe(hwq, hwq->depth, &psn_pg);
 	if (!IS_ALIGNED(fpsne, PAGE_SIZE))
-		indx_pad = ALIGN(fpsne, PAGE_SIZE) / size;
-
+		indx_pad = (fpsne & ~PAGE_MASK) / size;
 	hwq->pad_pgofft = indx_pad;
 	hwq->pad_pg = (u64 *)psn_pg;
 	hwq->pad_stride = size;
@@ -959,6 +961,7 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 	u16 cmd_flags = 0;
 	u32 qp_flags = 0;
 	u8 pg_sz_lvl;
+	u32 tbl_indx;
 	u16 nsge;
 
 	RCFW_CMD_PREP(req, CREATE_QP, cmd_flags);
@@ -1111,8 +1114,9 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 		rq->dbinfo.db = qp->dpi->dbr;
 		rq->dbinfo.max_slot = bnxt_qplib_set_rq_max_slot(rq->wqe_size);
 	}
-	rcfw->qp_tbl[qp->id].qp_id = qp->id;
-	rcfw->qp_tbl[qp->id].qp_handle = (void *)qp;
+	tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw);
+	rcfw->qp_tbl[tbl_indx].qp_id = qp->id;
+	rcfw->qp_tbl[tbl_indx].qp_handle = (void *)qp;
 
 	return 0;
 fail:
@@ -1457,10 +1461,12 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res,
 	struct cmdq_destroy_qp req;
 	struct creq_destroy_qp_resp resp;
 	u16 cmd_flags = 0;
+	u32 tbl_indx;
 	int rc;
 
-	rcfw->qp_tbl[qp->id].qp_id = BNXT_QPLIB_QP_ID_INVALID;
-	rcfw->qp_tbl[qp->id].qp_handle = NULL;
+	tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw);
+	rcfw->qp_tbl[tbl_indx].qp_id = BNXT_QPLIB_QP_ID_INVALID;
+	rcfw->qp_tbl[tbl_indx].qp_handle = NULL;
 
 	RCFW_CMD_PREP(req, DESTROY_QP, cmd_flags);
 
@@ -1468,8 +1474,8 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res,
 	rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req,
 					  (void *)&resp, NULL, 0);
 	if (rc) {
-		rcfw->qp_tbl[qp->id].qp_id = qp->id;
-		rcfw->qp_tbl[qp->id].qp_handle = qp;
+		rcfw->qp_tbl[tbl_indx].qp_id = qp->id;
+		rcfw->qp_tbl[tbl_indx].qp_handle = qp;
 		return rc;
 	}
 

drivers/infiniband/hw/bnxt_re/qplib_rcfw.c

@@ -307,14 +307,15 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw,
 	__le16  mcookie;
 	u16 cookie;
 	int rc = 0;
-	u32 qp_id;
+	u32 qp_id, tbl_indx;
 
 	pdev = rcfw->pdev;
 	switch (qp_event->event) {
 	case CREQ_QP_EVENT_EVENT_QP_ERROR_NOTIFICATION:
 		err_event = (struct creq_qp_error_notification *)qp_event;
 		qp_id = le32_to_cpu(err_event->xid);
-		qp = rcfw->qp_tbl[qp_id].qp_handle;
+		tbl_indx = map_qp_id_to_tbl_indx(qp_id, rcfw);
+		qp = rcfw->qp_tbl[tbl_indx].qp_handle;
 		dev_dbg(&pdev->dev, "Received QP error notification\n");
 		dev_dbg(&pdev->dev,
 			"qpid 0x%x, req_err=0x%x, resp_err=0x%x\n",
@@ -615,8 +616,9 @@ int bnxt_qplib_alloc_rcfw_channel(struct bnxt_qplib_res *res,
 
 	cmdq->bmap_size = bmap_size;
 
-	rcfw->qp_tbl_size = qp_tbl_sz;
-	rcfw->qp_tbl = kcalloc(qp_tbl_sz, sizeof(struct bnxt_qplib_qp_node),
+	/* Allocate one extra to hold the QP1 entries */
+	rcfw->qp_tbl_size = qp_tbl_sz + 1;
+	rcfw->qp_tbl = kcalloc(rcfw->qp_tbl_size, sizeof(struct bnxt_qplib_qp_node),
 			       GFP_KERNEL);
 	if (!rcfw->qp_tbl)
 		goto fail;

drivers/infiniband/hw/bnxt_re/qplib_rcfw.h

@@ -216,4 +216,9 @@ int bnxt_qplib_deinit_rcfw(struct bnxt_qplib_rcfw *rcfw);
 int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw,
 			 struct bnxt_qplib_ctx *ctx, int is_virtfn);
 void bnxt_qplib_mark_qp_error(void *qp_handle);
+static inline u32 map_qp_id_to_tbl_indx(u32 qid, struct bnxt_qplib_rcfw *rcfw)
+{
+	/* Last index of the qp_tbl is for QP1 ie. qp_tbl_size - 1*/
+	return (qid == 1) ? rcfw->qp_tbl_size - 1 : qid % rcfw->qp_tbl_size - 2;
+}
 #endif /* __BNXT_QPLIB_RCFW_H__ */

drivers/infiniband/hw/bnxt_re/qplib_sp.c

@@ -149,7 +149,7 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw,
 	attr->max_inline_data = le32_to_cpu(sb->max_inline_data);
 	attr->l2_db_size = (sb->l2_db_space_size + 1) *
 			    (0x01 << RCFW_DBR_BASE_PAGE_SHIFT);
-	attr->max_sgid = le32_to_cpu(sb->max_gid);
+	attr->max_sgid = BNXT_QPLIB_NUM_GIDS_SUPPORTED;
 
 	bnxt_qplib_query_version(rcfw, attr->fw_ver);
 

drivers/infiniband/hw/bnxt_re/qplib_sp.h

@@ -47,6 +47,7 @@
 struct bnxt_qplib_dev_attr {
 #define FW_VER_ARR_LEN			4
 	u8				fw_ver[FW_VER_ARR_LEN];
+#define BNXT_QPLIB_NUM_GIDS_SUPPORTED	256
 	u16				max_sgid;
 	u16				max_mrw;
 	u32				max_qp;

drivers/infiniband/hw/mlx4/main.c

@@ -784,7 +784,8 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port,
 	props->ip_gids = true;
 	props->gid_tbl_len	= mdev->dev->caps.gid_table_len[port];
 	props->max_msg_sz	= mdev->dev->caps.max_msg_sz;
-	props->pkey_tbl_len	= 1;
+	if (mdev->dev->caps.pkey_table_len[port])
+		props->pkey_tbl_len = 1;
 	props->max_mtu		= IB_MTU_4096;
 	props->max_vl_num	= 2;
 	props->state		= IB_PORT_DOWN;

drivers/infiniband/sw/rxe/rxe.c

@@ -40,6 +40,8 @@ MODULE_AUTHOR("Bob Pearson, Frank Zago, John Groves, Kamal Heib");
 MODULE_DESCRIPTION("Soft RDMA transport");
 MODULE_LICENSE("Dual BSD/GPL");
 
+bool rxe_initialized;
+
 /* free resources for a rxe device all objects created for this device must
  * have been destroyed
  */
@@ -315,6 +317,7 @@ static int __init rxe_module_init(void)
 		return err;
 
 	rdma_link_register(&rxe_link_ops);
+	rxe_initialized = true;
 	pr_info("loaded\n");
 	return 0;
 }
@@ -326,6 +329,7 @@ static void __exit rxe_module_exit(void)
 	rxe_net_exit();
 	rxe_cache_exit();
 
+	rxe_initialized = false;
 	pr_info("unloaded\n");
 }
 

drivers/infiniband/sw/rxe/rxe.h

@@ -67,6 +67,8 @@
 
 #define RXE_ROCE_V2_SPORT		(0xc000)
 
+extern bool rxe_initialized;
+
 static inline u32 rxe_crc32(struct rxe_dev *rxe,
 			    u32 crc, void *next, size_t len)
 {

drivers/infiniband/sw/rxe/rxe_mr.c

@@ -205,6 +205,7 @@ int rxe_mem_init_user(struct rxe_pd *pd, u64 start,
 			vaddr = page_address(sg_page_iter_page(&sg_iter));
 			if (!vaddr) {
 				pr_warn("null vaddr\n");
+				ib_umem_release(umem);
 				err = -ENOMEM;
 				goto err1;
 			}

drivers/infiniband/sw/rxe/rxe_sysfs.c

@@ -61,6 +61,11 @@ static int rxe_param_set_add(const char *val, const struct kernel_param *kp)
 	struct net_device *ndev;
 	struct rxe_dev *exists;
 
+	if (!rxe_initialized) {
+		pr_err("Module parameters are not supported, use rdma link add or rxe_cfg\n");
+		return -EAGAIN;
+	}
+
 	len = sanitize_arg(val, intf, sizeof(intf));
 	if (!len) {
 		pr_err("add: invalid interface name\n");

drivers/infiniband/sw/rxe/rxe_verbs.c

@@ -1056,7 +1056,7 @@ static ssize_t parent_show(struct device *device,
 	struct rxe_dev *rxe =
 		rdma_device_to_drv_device(device, struct rxe_dev, ib_dev);
 
-	return snprintf(buf, 16, "%s\n", rxe_parent_name(rxe, 1));
+	return scnprintf(buf, PAGE_SIZE, "%s\n", rxe_parent_name(rxe, 1));
 }
 
 static DEVICE_ATTR_RO(parent);

drivers/infiniband/ulp/isert/ib_isert.c

@@ -140,15 +140,15 @@ isert_alloc_rx_descriptors(struct isert_conn *isert_conn)
 	rx_desc = isert_conn->rx_descs;
 
 	for (i = 0; i < ISERT_QP_MAX_RECV_DTOS; i++, rx_desc++)  {
-		dma_addr = ib_dma_map_single(ib_dev, (void *)rx_desc,
-					ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+		dma_addr = ib_dma_map_single(ib_dev, rx_desc->buf,
+					ISER_RX_SIZE, DMA_FROM_DEVICE);
 		if (ib_dma_mapping_error(ib_dev, dma_addr))
 			goto dma_map_fail;
 
 		rx_desc->dma_addr = dma_addr;
 
 		rx_sg = &rx_desc->rx_sg;
-		rx_sg->addr = rx_desc->dma_addr;
+		rx_sg->addr = rx_desc->dma_addr + isert_get_hdr_offset(rx_desc);
 		rx_sg->length = ISER_RX_PAYLOAD_SIZE;
 		rx_sg->lkey = device->pd->local_dma_lkey;
 		rx_desc->rx_cqe.done = isert_recv_done;
@@ -160,7 +160,7 @@ isert_alloc_rx_descriptors(struct isert_conn *isert_conn)
 	rx_desc = isert_conn->rx_descs;
 	for (j = 0; j < i; j++, rx_desc++) {
 		ib_dma_unmap_single(ib_dev, rx_desc->dma_addr,
-				    ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+				    ISER_RX_SIZE, DMA_FROM_DEVICE);
 	}
 	kfree(isert_conn->rx_descs);
 	isert_conn->rx_descs = NULL;
@@ -181,7 +181,7 @@ isert_free_rx_descriptors(struct isert_conn *isert_conn)
 	rx_desc = isert_conn->rx_descs;
 	for (i = 0; i < ISERT_QP_MAX_RECV_DTOS; i++, rx_desc++)  {
 		ib_dma_unmap_single(ib_dev, rx_desc->dma_addr,
-				    ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+				    ISER_RX_SIZE, DMA_FROM_DEVICE);
 	}
 
 	kfree(isert_conn->rx_descs);
@@ -299,10 +299,9 @@ isert_free_login_buf(struct isert_conn *isert_conn)
 			    ISER_RX_PAYLOAD_SIZE, DMA_TO_DEVICE);
 	kfree(isert_conn->login_rsp_buf);
 
-	ib_dma_unmap_single(ib_dev, isert_conn->login_req_dma,
-			    ISER_RX_PAYLOAD_SIZE,
-			    DMA_FROM_DEVICE);
-	kfree(isert_conn->login_req_buf);
+	ib_dma_unmap_single(ib_dev, isert_conn->login_desc->dma_addr,
+			    ISER_RX_SIZE, DMA_FROM_DEVICE);
+	kfree(isert_conn->login_desc);
 }
 
 static int
@@ -311,25 +310,25 @@ isert_alloc_login_buf(struct isert_conn *isert_conn,
 {
 	int ret;
 
-	isert_conn->login_req_buf = kzalloc(sizeof(*isert_conn->login_req_buf),
+	isert_conn->login_desc = kzalloc(sizeof(*isert_conn->login_desc),
 			GFP_KERNEL);
-	if (!isert_conn->login_req_buf)
+	if (!isert_conn->login_desc)
 		return -ENOMEM;
 
-	isert_conn->login_req_dma = ib_dma_map_single(ib_dev,
-				isert_conn->login_req_buf,
-				ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
-	ret = ib_dma_mapping_error(ib_dev, isert_conn->login_req_dma);
+	isert_conn->login_desc->dma_addr = ib_dma_map_single(ib_dev,
+				isert_conn->login_desc->buf,
+				ISER_RX_SIZE, DMA_FROM_DEVICE);
+	ret = ib_dma_mapping_error(ib_dev, isert_conn->login_desc->dma_addr);
 	if (ret) {
-		isert_err("login_req_dma mapping error: %d\n", ret);
-		isert_conn->login_req_dma = 0;
-		goto out_free_login_req_buf;
+		isert_err("login_desc dma mapping error: %d\n", ret);
+		isert_conn->login_desc->dma_addr = 0;
+		goto out_free_login_desc;
 	}
 
 	isert_conn->login_rsp_buf = kzalloc(ISER_RX_PAYLOAD_SIZE, GFP_KERNEL);
 	if (!isert_conn->login_rsp_buf) {
 		ret = -ENOMEM;
-		goto out_unmap_login_req_buf;
+		goto out_unmap_login_desc;
 	}
 
 	isert_conn->login_rsp_dma = ib_dma_map_single(ib_dev,
@@ -346,11 +345,11 @@ isert_alloc_login_buf(struct isert_conn *isert_conn,
 
 out_free_login_rsp_buf:
 	kfree(isert_conn->login_rsp_buf);
-out_unmap_login_req_buf:
-	ib_dma_unmap_single(ib_dev, isert_conn->login_req_dma,
-			    ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
-out_free_login_req_buf:
-	kfree(isert_conn->login_req_buf);
+out_unmap_login_desc:
+	ib_dma_unmap_single(ib_dev, isert_conn->login_desc->dma_addr,
+			    ISER_RX_SIZE, DMA_FROM_DEVICE);
+out_free_login_desc:
+	kfree(isert_conn->login_desc);
 	return ret;
 }
 
@@ -476,7 +475,7 @@ isert_connect_release(struct isert_conn *isert_conn)
 	if (isert_conn->qp)
 		isert_destroy_qp(isert_conn);
 
-	if (isert_conn->login_req_buf)
+	if (isert_conn->login_desc)
 		isert_free_login_buf(isert_conn);
 
 	isert_device_put(device);
@@ -862,17 +861,18 @@ isert_login_post_recv(struct isert_conn *isert_conn)
 	int ret;
 
 	memset(&sge, 0, sizeof(struct ib_sge));
-	sge.addr = isert_conn->login_req_dma;
+	sge.addr = isert_conn->login_desc->dma_addr +
+		isert_get_hdr_offset(isert_conn->login_desc);
 	sge.length = ISER_RX_PAYLOAD_SIZE;
 	sge.lkey = isert_conn->device->pd->local_dma_lkey;
 
 	isert_dbg("Setup sge: addr: %llx length: %d 0x%08x\n",
 		sge.addr, sge.length, sge.lkey);
 
-	isert_conn->login_req_buf->rx_cqe.done = isert_login_recv_done;
+	isert_conn->login_desc->rx_cqe.done = isert_login_recv_done;
 
 	memset(&rx_wr, 0, sizeof(struct ib_recv_wr));
-	rx_wr.wr_cqe = &isert_conn->login_req_buf->rx_cqe;
+	rx_wr.wr_cqe = &isert_conn->login_desc->rx_cqe;
 	rx_wr.sg_list = &sge;
 	rx_wr.num_sge = 1;
 
@@ -949,7 +949,7 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login,
 static void
 isert_rx_login_req(struct isert_conn *isert_conn)
 {
-	struct iser_rx_desc *rx_desc = isert_conn->login_req_buf;
+	struct iser_rx_desc *rx_desc = isert_conn->login_desc;
 	int rx_buflen = isert_conn->login_req_len;
 	struct iscsi_conn *conn = isert_conn->conn;
 	struct iscsi_login *login = conn->conn_login;
@@ -961,7 +961,7 @@ isert_rx_login_req(struct isert_conn *isert_conn)
 
 	if (login->first_request) {
 		struct iscsi_login_req *login_req =
-			(struct iscsi_login_req *)&rx_desc->iscsi_header;
+			(struct iscsi_login_req *)isert_get_iscsi_hdr(rx_desc);
 		/*
 		 * Setup the initial iscsi_login values from the leading
 		 * login request PDU.
@@ -980,13 +980,13 @@ isert_rx_login_req(struct isert_conn *isert_conn)
 		login->tsih		= be16_to_cpu(login_req->tsih);
 	}
 
-	memcpy(&login->req[0], (void *)&rx_desc->iscsi_header, ISCSI_HDR_LEN);
+	memcpy(&login->req[0], isert_get_iscsi_hdr(rx_desc), ISCSI_HDR_LEN);
 
 	size = min(rx_buflen, MAX_KEY_VALUE_PAIRS);
 	isert_dbg("Using login payload size: %d, rx_buflen: %d "
 		  "MAX_KEY_VALUE_PAIRS: %d\n", size, rx_buflen,
 		  MAX_KEY_VALUE_PAIRS);
-	memcpy(login->req_buf, &rx_desc->data[0], size);
+	memcpy(login->req_buf, isert_get_data(rx_desc), size);
 
 	if (login->first_request) {
 		complete(&isert_conn->login_comp);
@@ -1051,14 +1051,15 @@ isert_handle_scsi_cmd(struct isert_conn *isert_conn,
 	if (imm_data_len != data_len) {
 		sg_nents = max(1UL, DIV_ROUND_UP(imm_data_len, PAGE_SIZE));
 		sg_copy_from_buffer(cmd->se_cmd.t_data_sg, sg_nents,
-				    &rx_desc->data[0], imm_data_len);
+				    isert_get_data(rx_desc), imm_data_len);
 		isert_dbg("Copy Immediate sg_nents: %u imm_data_len: %d\n",
 			  sg_nents, imm_data_len);
 	} else {
 		sg_init_table(&isert_cmd->sg, 1);
 		cmd->se_cmd.t_data_sg = &isert_cmd->sg;
 		cmd->se_cmd.t_data_nents = 1;
-		sg_set_buf(&isert_cmd->sg, &rx_desc->data[0], imm_data_len);
+		sg_set_buf(&isert_cmd->sg, isert_get_data(rx_desc),
+				imm_data_len);
 		isert_dbg("Transfer Immediate imm_data_len: %d\n",
 			  imm_data_len);
 	}
@@ -1127,9 +1128,9 @@ isert_handle_iscsi_dataout(struct isert_conn *isert_conn,
 	}
 	isert_dbg("Copying DataOut: sg_start: %p, sg_off: %u "
 		  "sg_nents: %u from %p %u\n", sg_start, sg_off,
-		  sg_nents, &rx_desc->data[0], unsol_data_len);
+		  sg_nents, isert_get_data(rx_desc), unsol_data_len);
 
-	sg_copy_from_buffer(sg_start, sg_nents, &rx_desc->data[0],
+	sg_copy_from_buffer(sg_start, sg_nents, isert_get_data(rx_desc),
 			    unsol_data_len);
 
 	rc = iscsit_check_dataout_payload(cmd, hdr, false);
@@ -1188,7 +1189,7 @@ isert_handle_text_cmd(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd
 	}
 	cmd->text_in_ptr = text_in;
 
-	memcpy(cmd->text_in_ptr, &rx_desc->data[0], payload_length);
+	memcpy(cmd->text_in_ptr, isert_get_data(rx_desc), payload_length);
 
 	return iscsit_process_text_cmd(conn, cmd, hdr);
 }
@@ -1198,7 +1199,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 		uint32_t read_stag, uint64_t read_va,
 		uint32_t write_stag, uint64_t write_va)
 {
-	struct iscsi_hdr *hdr = &rx_desc->iscsi_header;
+	struct iscsi_hdr *hdr = isert_get_iscsi_hdr(rx_desc);
 	struct iscsi_conn *conn = isert_conn->conn;
 	struct iscsi_cmd *cmd;
 	struct isert_cmd *isert_cmd;
@@ -1296,8 +1297,8 @@ isert_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	struct isert_conn *isert_conn = wc->qp->qp_context;
 	struct ib_device *ib_dev = isert_conn->cm_id->device;
 	struct iser_rx_desc *rx_desc = cqe_to_rx_desc(wc->wr_cqe);
-	struct iscsi_hdr *hdr = &rx_desc->iscsi_header;
-	struct iser_ctrl *iser_ctrl = &rx_desc->iser_header;
+	struct iscsi_hdr *hdr = isert_get_iscsi_hdr(rx_desc);
+	struct iser_ctrl *iser_ctrl = isert_get_iser_hdr(rx_desc);
 	uint64_t read_va = 0, write_va = 0;
 	uint32_t read_stag = 0, write_stag = 0;
 
@@ -1311,7 +1312,7 @@ isert_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	rx_desc->in_use = true;
 
 	ib_dma_sync_single_for_cpu(ib_dev, rx_desc->dma_addr,
-			ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+			ISER_RX_SIZE, DMA_FROM_DEVICE);
 
 	isert_dbg("DMA: 0x%llx, iSCSI opcode: 0x%02x, ITT: 0x%08x, flags: 0x%02x dlen: %d\n",
 		 rx_desc->dma_addr, hdr->opcode, hdr->itt, hdr->flags,
@@ -1346,7 +1347,7 @@ isert_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 			read_stag, read_va, write_stag, write_va);
 
 	ib_dma_sync_single_for_device(ib_dev, rx_desc->dma_addr,
-			ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+			ISER_RX_SIZE, DMA_FROM_DEVICE);
 }
 
 static void
@@ -1360,8 +1361,8 @@ isert_login_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 		return;
 	}
 
-	ib_dma_sync_single_for_cpu(ib_dev, isert_conn->login_req_dma,
-			ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+	ib_dma_sync_single_for_cpu(ib_dev, isert_conn->login_desc->dma_addr,
+			ISER_RX_SIZE, DMA_FROM_DEVICE);
 
 	isert_conn->login_req_len = wc->byte_len - ISER_HEADERS_LEN;
 
@@ -1376,8 +1377,8 @@ isert_login_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	complete(&isert_conn->login_req_comp);
 	mutex_unlock(&isert_conn->mutex);
 
-	ib_dma_sync_single_for_device(ib_dev, isert_conn->login_req_dma,
-				ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
+	ib_dma_sync_single_for_device(ib_dev, isert_conn->login_desc->dma_addr,
+				ISER_RX_SIZE, DMA_FROM_DEVICE);
 }
 
 static void

drivers/infiniband/ulp/isert/ib_isert.h

@@ -59,9 +59,11 @@
 				ISERT_MAX_TX_MISC_PDUS	+ \
 				ISERT_MAX_RX_MISC_PDUS)
 
-#define ISER_RX_PAD_SIZE	(ISCSI_DEF_MAX_RECV_SEG_LEN + 4096 - \
-		(ISER_RX_PAYLOAD_SIZE + sizeof(u64) + sizeof(struct ib_sge) + \
-		 sizeof(struct ib_cqe) + sizeof(bool)))
+/*
+ * RX size is default of 8k plus headers, but data needs to align to
+ * 512 boundary, so use 1024 to have the extra space for alignment.
+ */
+#define ISER_RX_SIZE		(ISCSI_DEF_MAX_RECV_SEG_LEN + 1024)
 
 /* Maximum support is 16MB I/O size */
 #define ISCSI_ISER_MAX_SG_TABLESIZE	4096
@@ -81,21 +83,41 @@ enum iser_conn_state {
 };
 
 struct iser_rx_desc {
-	struct iser_ctrl iser_header;
-	struct iscsi_hdr iscsi_header;
-	char		data[ISCSI_DEF_MAX_RECV_SEG_LEN];
+	char		buf[ISER_RX_SIZE];
 	u64		dma_addr;
 	struct ib_sge	rx_sg;
 	struct ib_cqe	rx_cqe;
 	bool		in_use;
-	char		pad[ISER_RX_PAD_SIZE];
-} __packed;
+};
 
 static inline struct iser_rx_desc *cqe_to_rx_desc(struct ib_cqe *cqe)
 {
 	return container_of(cqe, struct iser_rx_desc, rx_cqe);
 }
 
+static void *isert_get_iser_hdr(struct iser_rx_desc *desc)
+{
+	return PTR_ALIGN(desc->buf + ISER_HEADERS_LEN, 512) - ISER_HEADERS_LEN;
+}
+
+static size_t isert_get_hdr_offset(struct iser_rx_desc *desc)
+{
+	return isert_get_iser_hdr(desc) - (void *)desc->buf;
+}
+
+static void *isert_get_iscsi_hdr(struct iser_rx_desc *desc)
+{
+	return isert_get_iser_hdr(desc) + sizeof(struct iser_ctrl);
+}
+
+static void *isert_get_data(struct iser_rx_desc *desc)
+{
+	void *data = isert_get_iser_hdr(desc) + ISER_HEADERS_LEN;
+
+	WARN_ON((uintptr_t)data & 511);
+	return data;
+}
+
 struct iser_tx_desc {
 	struct iser_ctrl iser_header;
 	struct iscsi_hdr iscsi_header;
@@ -142,9 +164,8 @@ struct isert_conn {
 	u32			responder_resources;
 	u32			initiator_depth;
 	bool			pi_support;
-	struct iser_rx_desc	*login_req_buf;
+	struct iser_rx_desc	*login_desc;
 	char			*login_rsp_buf;
-	u64			login_req_dma;
 	int			login_req_len;
 	u64			login_rsp_dma;
 	struct iser_rx_desc	*rx_descs;

drivers/infiniband/ulp/rtrs/rtrs-srv-sysfs.c

@@ -152,13 +152,6 @@ static struct attribute_group rtrs_srv_stats_attr_group = {
 	.attrs = rtrs_srv_stats_attrs,
 };
 
-static void rtrs_srv_dev_release(struct device *dev)
-{
-	struct rtrs_srv *srv = container_of(dev, struct rtrs_srv, dev);
-
-	kfree(srv);
-}
-
 static int rtrs_srv_create_once_sysfs_root_folders(struct rtrs_srv_sess *sess)
 {
 	struct rtrs_srv *srv = sess->srv;
@@ -172,7 +165,6 @@ static int rtrs_srv_create_once_sysfs_root_folders(struct rtrs_srv_sess *sess)
 		goto unlock;
 	}
 	srv->dev.class = rtrs_dev_class;
-	srv->dev.release = rtrs_srv_dev_release;
 	err = dev_set_name(&srv->dev, "%s", sess->s.sessname);
 	if (err)
 		goto unlock;
@@ -182,16 +174,16 @@ static int rtrs_srv_create_once_sysfs_root_folders(struct rtrs_srv_sess *sess)
 	 * sysfs files are created
 	 */
 	dev_set_uevent_suppress(&srv->dev, true);
-	err = device_register(&srv->dev);
+	err = device_add(&srv->dev);
 	if (err) {
-		pr_err("device_register(): %d\n", err);
+		pr_err("device_add(): %d\n", err);
 		goto put;
 	}
 	srv->kobj_paths = kobject_create_and_add("paths", &srv->dev.kobj);
 	if (!srv->kobj_paths) {
 		err = -ENOMEM;
 		pr_err("kobject_create_and_add(): %d\n", err);
-		device_unregister(&srv->dev);
+		device_del(&srv->dev);
 		goto unlock;
 	}
 	dev_set_uevent_suppress(&srv->dev, false);
@@ -216,7 +208,7 @@ rtrs_srv_destroy_once_sysfs_root_folders(struct rtrs_srv_sess *sess)
 		kobject_del(srv->kobj_paths);
 		kobject_put(srv->kobj_paths);
 		mutex_unlock(&srv->paths_mutex);
-		device_unregister(&srv->dev);
+		device_del(&srv->dev);
 	} else {
 		mutex_unlock(&srv->paths_mutex);
 	}

drivers/infiniband/ulp/rtrs/rtrs-srv.c

@@ -1319,6 +1319,13 @@ static int rtrs_srv_get_next_cq_vector(struct rtrs_srv_sess *sess)
 	return sess->cur_cq_vector;
 }
 
+static void rtrs_srv_dev_release(struct device *dev)
+{
+	struct rtrs_srv *srv = container_of(dev, struct rtrs_srv, dev);
+
+	kfree(srv);
+}
+
 static struct rtrs_srv *__alloc_srv(struct rtrs_srv_ctx *ctx,
 				     const uuid_t *paths_uuid)
 {
@@ -1336,6 +1343,8 @@ static struct rtrs_srv *__alloc_srv(struct rtrs_srv_ctx *ctx,
 	uuid_copy(&srv->paths_uuid, paths_uuid);
 	srv->queue_depth = sess_queue_depth;
 	srv->ctx = ctx;
+	device_initialize(&srv->dev);
+	srv->dev.release = rtrs_srv_dev_release;
 
 	srv->chunks = kcalloc(srv->queue_depth, sizeof(*srv->chunks),
 			      GFP_KERNEL);